amit-jain commented on code in PR #771: URL: https://github.com/apache/jackrabbit-oak/pull/771#discussion_r1036694562
########## oak-blob-plugins/src/main/java/org/apache/jackrabbit/oak/plugins/blob/MarkSweepGarbageCollector.java: ########## @@ -405,13 +405,35 @@ protected void mark(GarbageCollectorFileState fs) throws IOException, DataStoreE // Mark all used references iterateNodeTree(fs, false); - + + // Get size + sizeBlobStoreReferences(fs, stats); + // Move the marked references file to the data store meta area if applicable GarbageCollectionType.get(blobStore).addMarked(blobStore, fs, repoId, uniqueSuffix); LOG.debug("Ending mark phase of the garbage collector"); } + private static void sizeBlobStoreReferences(GarbageCollectorFileState fs, GarbageCollectionOperationStats stats) + throws IOException { + try (LineIterator lineIterator = new LineIterator(new FileReader(fs.getMarkedRefs()))) { + lineIterator.forEachRemaining(line -> { + String id = line.split(DELIM)[0]; + long length = DataStoreBlobStore.BlobId.of(id).getLength(); + LOG.info("Blob {} has size {}", id, length); + + stats.getCollector().updateNumBlobReferences(1); + + if (length != -1) { + stats.getCollector().updateSizeBlobReferences(length); Review Comment: renamed to updateBlobReferencesSize, as above since all other methods have update -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: dev-unsubscr...@jackrabbit.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org